1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-28 06:22:57 +08:00
youtube-dl/youtube_dl/extractor/telebruxelles.py

60 lines
2.2 KiB
Python
Raw Normal View History

2014-11-22 20:34:29 +08:00
# coding: utf-8
from __future__ import unicode_literals
import re
2014-11-22 20:34:29 +08:00
from .common import InfoExtractor
class TeleBruxellesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)'
2014-11-22 20:34:29 +08:00
_TESTS = [{
'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
2014-11-22 20:34:29 +08:00
'info_dict': {
'id': '158856',
'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
'ext': 'mp4',
'title': 'Que risque lauteur dune fausse alerte à la bombe ?',
'description': 'md5:3cf8df235d44ebc5426373050840e466',
2014-11-23 16:44:42 +08:00
},
2014-11-22 20:34:29 +08:00
}, {
'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
'md5': 'dfe07ecc9c153ceba8582ac912687675',
2014-11-22 20:34:29 +08:00
'info_dict': {
'id': '158433',
'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
'ext': 'mp4',
'title': 'Futsal : Schaerbeek sincline 5-3 à Thulin',
'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
2014-11-23 16:44:42 +08:00
},
}, {
'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
'only_matching': True,
2014-11-23 16:44:42 +08:00
}]
2014-11-22 20:34:29 +08:00
def _real_extract(self, url):
2014-11-23 16:44:42 +08:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2014-11-22 20:34:29 +08:00
2014-11-23 16:44:42 +08:00
article_id = self._html_search_regex(
r"<article id=\"post-(\d+)\"", webpage, 'article ID', default=None)
2014-11-23 16:44:42 +08:00
title = self._html_search_regex(
r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
description = self._og_search_description(webpage, default=None)
2014-11-22 20:34:29 +08:00
2014-11-23 16:44:42 +08:00
rtmp_url = self._html_search_regex(
r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
2014-11-23 16:44:42 +08:00
webpage, 'RTMP url')
rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
self._sort_formats(formats)
2014-11-23 16:44:42 +08:00
return {
'id': article_id or display_id,
2014-11-23 16:44:42 +08:00
'display_id': display_id,
'title': title,
'description': description,
'formats': formats,
2014-11-23 16:44:42 +08:00
}